© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84193
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ল
    1.96
    ل
    1.91
    '
    1.91
    )
    1.86
    (
    1.78
    :
    1.69
    1
    1.66
    2
    1.65
    }
    1.62
    स
    1.59
    POSITIVE LOGITS
    า
    1.54
    ia
    1.53
    ı
    1.52
    ا
    1.52
    ை
    1.47
    وم
    1.39
    in
    1.34
    𝗶
    1.25
    𝘢
    1.20
    וס
    1.17
    Activations Density 0.000%

    No Known Activations